A professor at The University of Texas at Dallas hopes within the next 10 years, you’ll be driving an autonomous car that his research helped make possible.
![Cong Liu](/news/files/2021/03/liu-cong-preferred-600-2018-04.jpg)
Dr. Cong Liu
Dr. Cong Liu, assistant professor of computer science in the Erik Jonsson School of Engineering and Computer Science, is producing algorithmic and system solutions that process massive amounts of data in real time. This allows designers across several industries to develop GPU-accelerated embedded cyber-physical systems — intelligent engineering systems that interact with the physical environment and make autonomous control decisions such as autonomous vehicles and robotics.
Liu’s project, D3: Addressing Emerging Data-Induced Challenges in Embedded and Real-Time Systems, earned him a Faculty Early Career Development (CAREER) Award from the National Science Foundation, providing him more than $500,000 in funding over the next five years to further his research in autonomous driving.
“If successful, my research will provide a set of hardware/software-combined solutions that take the first step for making the execution of autonomous driving workloads controllable and predictable in a resource-constrained embedded automotive platform,” he said.
In other words: Your car will make driving decisions for you.
Embedded systems must monitor humans and the environment to make intelligent decisions, Liu said.
About CAREER Awards
![National Science Foundation logo](/news/files/2021/03/nsf-logo.jpg)
The Faculty Early Career Development Program supports junior faculty who exemplify the role of teacher-scholars through outstanding research and excellent education that are integrated in the mission of their organizations. The highly selective program is the National Science Foundation's most prestigious for junior faculty who are considered likely to become leaders in their field.
“The embedded system receives tens or maybe hundreds of data streams, which are recorded by a series of sensors and cameras,” said Liu, who has been at UT Dallas since 2013. “Each data stream needs to be processed in real time so that a decision can be made on whether the vehicle should accelerate, brake, turn left or turn right. If the data is not processed in real time, then the system fails.”
Liu said the camera sensors have to process and analyze huge amounts of data using a limited amount of storage space. The data is not in the cloud, or on a desktop or server.
“It needs to be in a small space in a car, using small wattage,” he said. “This becomes a significant challenge because it’s difficult to have enough computing capability to process all these complicated data streams in real time, and intelligently figure out what to do for the next 15 milliseconds. My proposal puts forth a set of techniques ranging from the application level to run-time resource scheduling and location, all the way down to system-level implementation and design.”
Liu is confident that driverless vehicles will be in full swing in 10 years, with limited routes within the next five.
“I think vehicles containing a good set of driver-assisted or even driverless tools will be the norm in five to 10 years as researchers overcome major obstacles in different domains, including computer vision, operating systems and algorithms. Some of the tools such as lane following and auto parking are already available in many of the cars we can buy today,” he said.
Project Adds New Dimensions to Data Analysis
When you think of geometry, you might think of mathematical equations involving the size, shape and position of objects, and the properties of space. And you’d be right.
But what if you could take these geometric principles, feed them into a computer and apply them to large amounts of data, so you could “see” the data expressed as a shape that helps you understand some of the data’s properties?
![Dr. Benjamin Raichel](/news/files/2021/03/raichel-benjamin-600-2018-03.jpg)
Dr. Benjamin Raichel
Dr. Benjamin Raichel, assistant professor of computer science, recently received a National Science Foundation Early Career Development (CAREER) Award for a project that does just that.
Raichel said his research will contribute to the idea of a geometric take on data analysis that will make it both faster and easier to manipulate large amounts of information.
He admits it’s an abstract concept.
“One of the main benefits of the grant is trying to get researchers to use these geometric insights in handling their data,” he said. “If you understand the geometry of your data, that can improve performance, running time and classification.”
The five-year grant, totaling nearly $500,000, will support his project called Giving Form to Data with a Geometric Scaffold. Raichel said using geometry to structure data and the world around us sounds like a new idea, but it actually dates back to the time of Plato and Aristotle.
“Geometry is something deeply ingrained in us as humans,” said Raichel, who joined the faculty of the Erik Jonsson School of Engineering and Computer Science in 2015. “This is why it’s one of the oldest branches in mathematics. It’s something we can reason about. We understand geometry at an intuitive level.”
Today’s data sets, especially in areas such as machine learning, are often massive and high-dimensional. For example, when trying to classify news articles, each article might be represented as a point where the frequency of each word is a different dimension. This leads to high-dimensional spaces that are hard to understand and where low-dimensional tools break down, what noted mathematician Richard Bellman dubbed the “curse of dimensionality.”
Raichel's approach is to map to a smaller and simpler subset of the data points that keep the same geometric structure. He said this allows for a more efficient computation of the data and can improve results by removing extraneous information.
“The goal is to identify the geometric structure of the data, summarize it and embed it into a simpler space where computations can be done more efficiently,” Raichel said. “The ultimate purpose is to develop better algorithms for handling data, whether it be for clustering, classification or any number of other computational tasks.”
Raichel will also use his CAREER grant to support student research in the field, develop new courses and organize seminars to raise the profile of using geometry to give form to data.